Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly/openWorld/idempotent; the description adds substantive behavior well beyond that — it discloses the well-known URL it fetches, that it validates the file, the handoff protocol (owner initiates), the payout policy (humans only, never agents), and what changes when referral_code is supplied. This is the kind of domain context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense paragraph, front-loaded with the resource and URL, then the contents, then the referral_code behavior, then the spec link. Every clause carries information, though the stacked parentheticals make it slightly harder to scan than a bulleted or shorter form would be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must convey what comes back — and it does, listing the file's content categories and the handoff link produced when referral_code is passed. With only two well-documented parameters and explicit safety annotations, nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: referral_code is the code of the human you work for and its effect is to return a handoff link carrying that code. That is an outcome-level explanation the schema's '3-24 letters/numbers' constraint does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (read and validate) plus a specific resource (a business's Open Agent Referral file at /.well-known/agent-referral.json), and enumerates the content it returns: offers, referral conditions, handoff mechanics, payee rules. Nothing among the sibling tools (bulletins, wall, messaging) overlaps, so an agent can route here unambiguously.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear conditional: pass referral_code to obtain the handoff link, omit it to just read the offer. The workflow constraint that the owner always starts the conversation and that only verified humans get paid is stated. It stops short of explicitly naming when NOT to use this versus another tool, but no sibling offers a real alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.